Triple
T14780721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tales of Dunk and Egg |
E347381
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Egg |
E1013742
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Egg | Statement: [Tales of Dunk and Egg, mainCharacter, Egg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Egg Context triple: [Tales of Dunk and Egg, mainCharacter, Egg]
-
A.
Egg
chosen
Egg is the young Targaryen prince Aegon V, who travels incognito as the squire of hedge knight Ser Duncan the Tall in George R.R. Martin’s Dunk and Egg stories.
-
B.
Egg
Egg is a Swiss municipality in the canton of Zurich, known for its rural character and proximity to the city of Zurich.
-
C.
Hen Egg
The Hen Egg is a jeweled Imperial Fabergé egg, renowned as one of the earliest and most iconic examples of the luxurious Easter eggs crafted for the Russian royal family.
-
D.
Big Egg
Big Egg is the popular nickname for the Tokyo Dome, a large indoor baseball stadium in Tokyo that hosts the Yomiuri Giants and major sporting and entertainment events.
-
E.
The Egg
The Egg is a modern, student-centered dining and learning facility at the Culinary Institute of America’s Hyde Park campus that showcases culinary education in a real-world restaurant environment.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9c7cac8190ba900df95e42e318 |
completed | April 14, 2026, 11:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0d00d46c8190b6289a9b8511a8fb |
completed | May 8, 2026, 4:19 p.m. |
Created at: April 10, 2026, 1:31 a.m.